Sakana AI paper: Neural nets can learn well while following biological rules
TheTuringPost · x · 2026-07-31
A recent paper from Sakana AI explores whether artificial neural networks need to follow the brain's Dale's principle (where each neuron is strictly excitatory or inhibitory).
- Methodology: Researchers separated excitatory and inhibitory signals and abandoned standard backpropagation. Instead, they used an Error Diffusion (ED) method, which shares a broad error signal across layers without transporting exact weight copies backward, making it more biologically plausible.
- Results: The network achieved 96.7% accuracy on MNIST and 61.7% on CIFAR-10. It also handled image classification, reinforcement learning, and simulated robot control reasonably well, though falling short of top-tier conventional networks.
- Conclusion: This suggests that biologically plausible learning is possible but not strictly necessary. Much like building airplanes didn't require copying birds exactly, AI might not need a perfect brain replica, though biology can still offer valuable inspirations.
Related event: Sakana AI Explores Biologically-Constrained Neural Networks(3 posts)→
More from Research
- Circulation Journal Reviews Generative and Agentic AI in Drug Discovery — james_y_zou · 2026-07-31
- Qwen Releases Technical Report for Qwen-Audio-3.0-Gen-Preview — udmrzn · 2026-07-31
- Demystifying the Core Math Behind Large Language Models — udmrzn · 2026-07-31
- Paper Evaluates Current Tools for Detecting Hallucinated AI Citations — RexDouglass · 2026-07-31
- Study: AI Writing Detectors Have High False Negative Rates, Unreliable for Serious Use — burkov · 2026-07-31
- TMLR Submissions 4x'd: AI-Generated Junk Forces Academic Gatekeeping — thegautamkamath · 2026-07-31